Sex classification via 2D-skeletonization

Abstract

Sex classification is a challenging open problem in computer vision. It is useful from statistics up to people recognition on surveillance video. So far, the best performance can be achieved by using 3D cameras, but this approach requires the use of some especial hardware. Other 2D approaches achieve good results on normal situations but fail when the person wears loose clothing and carries bags or the camera angle changes as they rely on calculating borders, silhouettes, or the energy of the person in the image. This work aims to provide a novel sex classification methodology based on the creation of a virtual skeleton for each individual from 2D images and video; then, the distances between some points of the skeleton are measured and work as input of a sex classifier. This improves the results since clothing, bags, and the camera angle affect little the skeletonization process.